Qwen2-7B: benchmark scores, price and ranking

Qwen2-7B from Qwen ranks #659 of 743 LLMs on the LLMs Tiger aggregate benchmark score (43.9), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Qwen
Type: Open-weight / local model
Open weights: Yes
Aggregate rank: #659 of 743 (score 43.9)

Across the 2 benchmarks where at least ten models are scored, Qwen2-7B is in the top 10% on 0 and in the top half on 0.

Qwen2-7B benchmark results

Qwen2-7B benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
MMLU-Pro	40.7%	#99 of 136	HuggingFace MMLU-Pro leaderboard	2026-10-13
GSM8K	79.9%	#15 of 17	HuggingFace GSM8K leaderboard	2026-10-13

About Qwen2-7B

Qwen2-7B is an open-weight model that can run on your own hardware from Qwen. No API price is listed for it yet. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Qwen2-7B stands

On our aggregate score, Qwen2-7B is #659 of 743 ranked models, in the lower half. Its score is 43.9; the scale is centred on 50, so it sits 6.1 points below the typical model. That beats 11% of the ranked field. Among the 23 ranked Qwen models it is #19. The next one up is Qwen1.5-7B-Chat at 44.3. The next one down is Qwen2-1.5B-Instruct at 43.4.

Qwen2-7B, benchmark by benchmark

Qwen2-7B lands below the middle on MMLU-Pro: 40.7%, #99 of 136, with 72% of the field scoring higher. Darwin-180B-RSI leads at 88.1%; the closest result above is MAmmoTH2-7B-Plus at 40.9%. It covers 57-subject knowledge + reasoning. The board median is 55.3%, so Qwen2-7B is 14.5 points below it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.

GSM8K is a weak spot. Qwen2-7B scores 79.9%, #15 of 17, behind 82% of the models measured. The leader, mimo-v2.5-pro, reaches 99.6%. It covers grade-school math word problems. The board median is 86.9%, so Qwen2-7B is 7.0 points below it. Source: HuggingFace GSM8K leaderboard, captured 2026-10-13.

Strengths and weaknesses

Qwen2-7B has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Reading these numbers

The 2 scores on this page come from 2 sources: HuggingFace GSM8K leaderboard (1), HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#656 Hermes-2-Theta-Llama-3-70B (44.0)
#657 qwen2-72b-instruct (43.9)
#658 ollama/hermes3 (43.9)
#660 gemini-1.5-pro-002 (43.9)
#661 GPT-5 nano (high) (43.8)
#662 gemma-2-27b-it (43.8)